New AutoFinetune: run: v0.3.0

special_tokens_map.json

@@ -1,4 +1,11 @@
 {
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,
@@ -6,15 +13,22 @@
     "rstrip": false,
     "single_word": false
   },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "[MASK]",
-    "lstrip": false,
+    "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -28,7 +42,7 @@
     "single_word": false
   },
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,31 +32,27 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "keep_accents": false,
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }